Research map / Label-efficient and robust learning / Recognition and long-tail
ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
Zhiyu Zheng, Shaoyu Chen, Haoran Yin, Xinbang Zhang, Jialv Zou, Xinggang Wang, Qian Zhang, Lefei Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ranker to base model (ablation) | ResAD base · NAVSIM v1 navtest | PDMS: 84.9 -> 85.1 | No clear effect |
| add trajectory residual modeling (TRM) (ablation) | ResAD base + Ranker · NAVSIM v1 navtest | PDMS: 85.1 -> 86.3 | Improved |
| add trajectory residual modeling (TRM) (ablation) | ResAD base + Ranker · NAVSIM v1 navtest | EP: 77.8 -> 80.3 | Improved |
| add point-wise residual normalization (PRNorm) (ablation) | ResAD with TRM · NAVSIM v1 navtest | PDMS: 86.3 -> 87.2 | Improved |
| add inertial reference perturbation (IRP) (ablation) | ResAD with TRM and PRNorm · NAVSIM v1 navtest | PDMS: 87.2 -> 88.8 | Improved |
| add inertial reference perturbation (IRP) (ablation) | ResAD with TRM and PRNorm · NAVSIM v1 navtest | EP: 81.4 -> 83.4 | Improved |
| add TRM to Transfuser | Transfuser · NAVSIM v1 navtest | PDMS: 84.0 -> 85.2 | Improved |
| add PRNorm on top of TRM | Transfuser · NAVSIM v1 navtest | PDMS: 85.2 -> 85.6 | Improved |
| add TRM to Transfuser_DP | Transfuser_DP · NAVSIM v1 navtest | PDMS: 84.5 -> 85.5 | Improved |
| add PRNorm on top of TRM | Transfuser_DP · NAVSIM v1 navtest | PDMS: 85.5 -> 85.8 | Improved |
| add PRNorm on top of TRM | Transfuser · NAVSIM v1 navtest | EP: 80.0 -> 79.8 | Hurt |
| replace static vocabulary with perturbed inertial references | DiffusionDrive · NAVSIM v1 navtest | mean candidate PDMS (P_m): 60.3 -> 86.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Transfuser — TransFuser: Imitation With Transformer-Based Sensor Fusion for Autonomous Driving (TPAMI 2022) · better on 2 of 2 shared results
- VADv2 — VADv2: End-to-End Autonomous Driving via Probabilistic Planning (ICLR 2026) · better on 1 of 1 shared result
- DriveSuprim — DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning (AAAI 2026) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving (ICLR 2026 · similarity 0.88)
- Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving (CVPR 2025 · similarity 0.87)
- Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving (NeurIPS 2024 · similarity 0.86)
- C2F-TP: A Coarse-to-Fine Denoising Framework for Uncertainty-Aware Trajectory Prediction (AAAI 2025 · similarity 0.86)
- LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations (NeurIPS 2024 · similarity 0.85)
- Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
